The first BlockDAG built for decentralized AI inference. Optimistic proofs. Unstoppable intelligence.
Three corporations control the filters of global AI. On-chain agents can't run local models. They need a decentralized inference layer.
AI providers quietly modify model outputs to align with corporate policies. No transparency, no audit trail, no recourse.
Every query passes through centralized servers. Your questions, strategies, and private data — logged, analyzed, monetized.
The model runs across thousands of sovereign miners. No kill switch. Intelligence becomes a public infrastructure.
Miners lock tokens on every response. Anyone can challenge. Cheaters lose everything. Honesty is the only profitable strategy.
Respond first, verify only when challenged. Fast, practical, cryptographically secure.
User or AI agent submits an AI_Request to the mempool with model ID and fees.
Miner runs the SLM on their GPU, publishes the response instantly, and locks a collateral as guarantee.
For 36,000 blocks (~1h), any verifier can re-run the deterministic model and dispute the result. Fraud proven on-chain via re-execution — miner's escrow is slashed.
No challenge — result is final, miner earns reward. Fraud proven — miner is slashed, challenger is rewarded.
No users yet? The protocol self-generates synthetic inference tasks derived from the previous block hash. Miners stay active, the network stays warm, infrastructure is battle-tested before the first real request.
When a consensus-level vulnerability was found post-launch, we shipped a mandatory hardfork before any exchange listing — deliberately. Coordinating a hardfork under listing pressure creates far more friction than a few days of delay. A clean consensus from day one is worth it. Network integrity comes first. Always.
Every model is identified by sha2-256(weight_file) — the hash extracted directly from its IPFS CID. A miner cannot fake which model it runs. Requesters set a priority_fee above the minimum to be served first.
Fast, lightweight. Ideal for short classification tasks, synthetic workloads, and high-frequency agent calls.
Balanced reasoning and speed. Suitable for complex queries, on-chain agent decisions, and multi-step logic.
High-fidelity reasoning at scale. For tasks requiring deep analysis, code generation, and long-context understanding.
State-of-the-art open model. Maximum intelligence. Reserved for the most demanding autonomous agent workflows.
Requesters can bid above the minimum to jump the queue. Miners serve the highest-paying requests first — creating a real market for inference priority. Every fee is paid in $KRX, creating direct, measurable buy pressure from actual AI usage.
Whether for humans seeking truth without filters or autonomous agents operating on-chain, Keryx is the trustless backbone of decentralized intelligence.
Smart contracts on Ethereum or Solana are deterministic — they cannot reason, interpret language, or make decisions. With Keryx, an agent broadcasts an AiRequest on-chain, a miner executes the inference, and the result comes back as a verifiable AiResponse — no HTTP call, no API key, no corporate gateway. The response is backed by real economic stake: fraudulent answers are slashable. The chain is the oracle.
Legal, medical, or political queries without corporate filters. A neutral AI that answers factually regardless of the topic.
Roadmap: users encrypt their prompt with the miner's public key before broadcasting. The miner decrypts and runs inference locally — the plaintext prompt never appears on-chain in any form. The OPoI commitment covers the result, preserving full fraud-proof guarantees on the output while keeping the query private.
Designed for long-term scarcity. Every transaction destroys value. Every block splits reward between miners, infrastructure, and protocol burn.
Fork rusty-kaspa. Anti-ASIC memory-hard PoW. Candle integration. Mandatory synthetic inference from block 1. Every miner runs a model.
Escrow collateral system. 36,000-block challenge window (~1h). Optimistic Proof of Inference live. Deflationary tokenomics with fee burn.
Production network running. Miners serving real inference tasks alongside synthetic work. Block explorer, public API, and web wallet fully operational.
Consensus-level model identity enforcement. model_id = sha2-256(weight_file) — unforgeable, derived from IPFS CID. AiResponse moves on-chain as a standalone tx with IPFS CID commitment. Four certified models: TinyLlama 1.1B, DeepSeek-R1 8B/32B, LLaMA 3.3 70B. Priority fees. Miners who haven't updated are rejected by consensus.
Ethereum + Solana bridges: smart contract → AiRequest → Keryx → result → on-chain callback. Autonomous on-chain agent demo. Encrypted prompt submission via miner pubkey.